| CPC G01V 5/045 (2013.01) [G01V 20/00 (2024.01); G06F 30/12 (2020.01)] | 15 Claims |
|
1. A method, comprising:
acquiring, with a Magnetic Resonance (MR) scanner or a pulse Nuclear Magnetic Resonance (NMR) logging tool that generates a magnetic field and measures a presence of protons in the magnetic field, first NMR data and permeability data regarding a geological region of interest;
wherein the first NMR data is organized according to one or more T2 signal parameters,
obtaining a plurality of ratio values of free fluids volume index (FFI) over bound fluids volumes (BFV) regarding the geological region of interest;
wherein the values of BFV are is determined based on the sum of a BFI value and a value for clay bound water,
wherein the plurality of ratio values comprises bulk volume irreducible (BVI) values and FFI values from training wells and a target well;
obtaining, by a computer processor, the acquired first NMR data and the acquired permeability data regarding the geological region of interest;
determining, by the computer processor using the plurality of ratio values, and using a neural network and second NMR data, first predicted permeability data regarding a predetermined formation within the geological region of interest, wherein the neural network is trained using the first NMR data and the acquired permeability data;
determining, by the computer processor, a predetermined fracture size within the predetermined formation based on the first predicted permeability data;
determining, by the computer processor, a predetermined type of lost circulation material (LCM) based on the predetermined fracture size;
transmitting, by the computer processor, a command to a well system that triggers a well operation using the predetermined type of LCM,
wherein the well operation is a drilling operation that supplies a drilling fluid with a predetermined LCM material into a wellbore coupled to the well system, and
wherein the predetermined LCM material corresponds to the predetermined type of LCM,
determining a training filter based on one or more geological parameters, wherein the one or more geological parameters correspond to a predetermined grain density, a predetermined core porosity, a predetermined core permeability, or a predetermined NMR porosity;
wherein the training filter comprises one or more filter ranges configured to filter NMR data from training wells and the target well, and
determining filtered NMR data using the training filter and the first NMR data,
where the neural network is trained using the filtered NMR data.
|